I am using VS with CUDA 13.1, I also tried cccl from Github to replace the one that comes with CUDA
Here is the compiler command as given by VS:
C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 13.1.targets(803,9): error MSB3721: The command ““C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\bin\nvcc.exe” -gencode=arch=compute_86,code=“sm_86,compute_86” --use-local-env -ccbin “C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.44.35207\bin\HostX64\x64” -x cu -rdc=true -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\lib\cmake\thrust…\thrust” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\lib\cmake\libcudacxx…\libcudacxx\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\lib\cmake\cub…\cub" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\thrust" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\libcudacxx\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\cccl\cub" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1\include" -G --keep-dir x64\Debug -maxrregcount=0 --machine 64 --compile -cudart static /Zc:preprocessor -g -D_WINDOWS -DCCCL_ENABLE_ASSERTIONS -DTHRUST_DEVICE_SYSTEM=THRUST_DEVICE_SYSTEM_CUDA -DNOMINMAX -D/Zc:preprocessor -DWIN64 -D_DEBUG -D_CONSOLE -DHAVE_CXX17 -DCCCL_IGNORE_DEPRECATED_CPP_DIALECT -D/Zc:preprocessor -D_MBCS -Xcompiler “/EHsc /W4 /nologo /Od /FS /Zi /RTC1 /MTd /GR” -Xcompiler “/Fdx64\Debug\vc143.pdb” -o “C:\Users\dajim\Documents\Visual Studio 2022\projects\CudaFillTest\CudaFillTest\x64\Debug\FillTest.cu.obj” “C:\Users\dajim\Documents\Visual Studio 2022\projects\CudaFillTest\CudaFillTest\FillTest.cu”" exited with code 1. [C:\Users\dajim\Documents\Visual Studio 2022\projects\CudaFillTest\CudaFillTest\CudaFillTest.vcxproj]
I looked the error up on google and many suggest that is a problem with the compile command
Can someone from NVIDIA look at it and see what could be wrong with it? or suggest a way to fix this error